Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2073 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.4189. Min Act: -0.0000

Data Index: 1030720 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.5187. Min Act: -0.0000

Data Index: 1388504 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.3032. Min Act: -0.0001

Data Index: 1254636 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.2437. Min Act: -0.0000

Data Index: 272898 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.4214. Min Act: -0.0000

Data Index: 457249 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.1731. Min Act: -0.0000

Data Index: 1258895 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.1844. Min Act: -0.0000

Data Index: 904292 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.3434. Min Act: -0.0001

Data Index: 1216690 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 2.5187. Min Range: -2.5187

Max Act: 1.9134. Min Act: -0.0000

Data Index: 235799 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.0331. Min Act: -0.0000

Data Index: 19184 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.0942. Min Act: -0.0000

Data Index: 1547000 (Python Code)

Max Activating Token Index: 635

Text #11

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.0629. Min Act: -0.0000

Data Index: 824368 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.0553. Min Act: -0.0000

Data Index: 1353175 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.0492. Min Act: -0.0001

Data Index: 103097 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.0347. Min Act: -0.0000

Data Index: 155823 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 2.5187. Min Range: -2.5187

Max Act: 1.8902. Min Act: -0.0001

Data Index: 1110087 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 2.5187. Min Range: -2.5187

Max Act: 1.9235. Min Act: -0.0001

Data Index: 813876 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.0165. Min Act: -0.0000

Data Index: 956158 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.0052. Min Act: -0.0000

Data Index: 485502 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 2.5187. Min Range: -2.5187

Max Act: 2.0377. Min Act: -0.0001

Data Index: 190022 (C4 (Web Text))

Max Activating Token Index: 34